Paper ID: 2111.14787

Comparison of Models for Training Optical Matrix Multipliers in Neuromorphic PICs

Ali Cem, Siqi Yan, Uiara Celine de Moura, Yunhong Ding, Darko Zibar, Francesco Da Ros

We experimentally compare simple physics-based vs. data-driven neural-network-based models for offline training of programmable photonic chips using Mach-Zehnder interferometer meshes. The neural-network model outperforms physics-based models for a chip with thermal crosstalk, yielding increased testing accuracy.

Submitted: Nov 23, 2021